My research focuses on advancing real-time structural health monitoring (SHM) through data-driven diagnostics, sparse sensor analytics, and intelligent algorithms. At the intersection of civil, mechanical, and aerospace systems, my work addresses the growing need for resilient infrastructure by developing computational tools that transform sensor data into actionable insights - especially when measurements are limited, noisy, or intermittently available.

I design adaptive, physics-informed algorithms that enable online modal identification, condition assessment, and anomaly detection in structural systems. A core application area of my work is in renewable energy infrastructure, with a strong emphasis on wind turbines. Through predictive analytics and downtime detection, I aim to reduce failure risk, optimize maintenance, and extend the lifecycle of critical assets.

As the lead of the OSCAR (Online Structural Control and Monitoring) group, I focus on creating digital twins of real-world structures by fusing physical models with real-time sensor data. Our multidisciplinary methods span system identification, vibration analysis, time-series modeling, and machine learning. From bridges and buildings to turbines and rail systems, our tools support smart decision-making and autonomous diagnostics.

With recognition including the MILCA Award by CII, Best Reviewer at CTCS 2022, and the Research Excellence Award at the MaREI Symposium, I continue to collaborate across disciplines to integrate real-time SHM into mainstream safety and design frameworks. I am keen to connect with researchers and partners committed to sustainable, intelligent infrastructure.

My research explores the intersection of structural mechanics, smart monitoring technologies, and sustainable infrastructure systems. I am particularly interested in developing real-time data-driven methods for assessing the health and performance of critical infrastructure and renewable energy assets. Through computational intelligence, machine learning, and advanced signal processing, my work aims to improve the resilience, reliability, and operational efficiency of built environments. A central focus of my research is translating these techniques into scalable, low-cost, and field-deployable solutions that can inform asset management and policy-making.

• Real-Time Structural Health Monitoring of Built Infrastructures: 
  Development of efficient vibration-based damage detection algorithms that enable objective assessment of system performance, damage localization, intensity estimation, and remaining service life under operational and environmental loads.
• Real-Time Downtime Detection of Renewable Energy Devices:
  Investigation of anomaly detection frameworks using sensor data and smart instrumentation to identify faults and performance degradation in wind turbines. Current studies explore classifier-based detection, calibrated using wind speed and power metrics within a kNN-based structure.
• Single-Sensor Based Real-Time Infrastructure Monitoring:
  Advanced Recursive Singular Spectrum Analysis (RSSA) methods support real-time fault detection, filtering, and modal identification using minimal sensor setups. This approach enhances scalability, replicability, and cost-effectiveness for large-scale deployment.
• Online Bridge Monitoring: Scour, Variable Damping, and Rehabilitation:
  Addressing challenges in railway bridge monitoring through dynamic characterization before and after scour damage and repair. Applications include field instrumentation and vibration-based scour detection using energy harvesting devices, with signal processing via singular spectrum analysis to enhance signal integrity.

International media coverage: 

1. DSRL wins at the Irish Laboratory Awards: https://www.ucd.ie/eacollege/newsandevents/2020newsarchive/theirishlaboratoryawards2020/
2. Commendable performance by interdisciplinary researchers at DSRL: https://www.labawards.ie/2020-winners

• Real-time structural health monitoring (SHM)
• Renewable energy system diagnostics
• Advanced signal processing and time-series analysis
• Experimental design and field instrumentation
• Computational modeling and machine learning integration

• AI-driven downtime detection for wind energy systems
• Machine learning-based fault diagnostics for critical infrastructure
• Real-time SHM frameworks for predictive maintenance in industry
• Cost-effective sensor deployment strategies using single-sensor analytics
• Scour detection and rehabilitation assessment for aging bridges

Ph.D. in Structural Engineering